Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "</think>": 166104,
+  "</tool_call>": 166106,
+  "<think>": 166103,
+  "<tool_call>": 166105,
+  "<|endoftext|>": 166102,
+  "<|im_end|>": 166101,
+  "<|im_start|>": 166100
+}

chat_template.jinja

@@ -0,0 +1,137 @@
+
+        {%- if tools %}
+            {{- '<|im_start|>system
+' }}
+            {%- if messages[0].role == 'system' %}
+                {{- messages[0].content + '
+
+' }}
+            {%- else %} 
+                {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。
+如果没有一个函数可以使用，请直接使用自然语言回复用户。
+如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。
+如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} 
+            {%- endif %}
+            {{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" }}
+            {%- for tool in tools %}
+                {{- "
+" }}
+                {{- tool | tojson }}
+            {%- endfor %}
+            {{- "
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{\"name\": <function-name>, \"arguments\": <args-json-object>}
+</tool_call><|im_end|>
+" }}
+        {%- else %}
+            {%- if messages[0].role == 'system' %}
+                {{- '<|im_start|>system
+' + messages[0].content + '<|im_end|>
+' }}
+            {%- else %} 
+                {{- '<|im_start|>system
+你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>
+' }} 
+            {%- endif %}
+        {%- endif %}
+        {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+        {%- for message in messages[::-1] %}
+            {%- set index = (messages|length - 1) - loop.index0 %}
+            {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+                {%- set ns.multi_step_tool = false %}
+                {%- set ns.last_query_index = index %}
+            {%- endif %}
+        {%- endfor %}
+        {%- for message in messages %}
+            {%- if message.content is string %}
+                {%- set content = message.content %}
+            {%- else %}
+                {%- set content = '' %}
+            {%- endif %}
+            {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+                {{- '<|im_start|>' + message.role + '
+' + content + '<|im_end|>' + '
+' }}
+            {%- elif message.role == "assistant" %}
+                {%- set reasoning_content = '' %}
+                {%- if message.reasoning_content is string %}
+                    {%- set reasoning_content = message.reasoning_content %}
+                {%- else %}
+                    {%- if '</think>' in content %}
+                        {%- set reasoning_content = content.split('</think>')[0].rstrip('
+').split('<think>')[-1].lstrip('
+') %}
+                        {%- set content = content.split('</think>')[-1].lstrip('
+') %}
+                    {%- endif %}
+                {%- endif %}
+                {%- if loop.index0 > ns.last_query_index or keep_all_think or (extra_body is defined and extra_body.keep_all_think) %}
+                    {%- if loop.last or (not loop.last and reasoning_content) %}
+                        {{- '<|im_start|>' + message.role + '
+<think>
+' + reasoning_content.strip('
+') + '
+</think>
+
+' + content.lstrip('
+') }}
+                    {%- else %}
+                        {{- '<|im_start|>' + message.role + '
+' + content }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '<|im_start|>' + message.role + '
+' + content }}
+                {%- endif %}
+                {%- if message.tool_calls %}
+                    {%- for tool_call in message.tool_calls %}
+                        {%- if (loop.first and content) or (not loop.first) %}
+                            {{- '
+' }}
+                        {%- endif %}
+                        {%- if tool_call.function %}
+                            {%- set tool_call = tool_call.function %}
+                        {%- endif %}
+                        {{- '<tool_call>
+{"name": "' }}
+                        {{- tool_call.name }}
+                        {{- '", "arguments": ' }}
+                        {%- if tool_call.arguments is string %}
+                            {{- tool_call.arguments }}
+                        {%- else %}
+                            {{- tool_call.arguments | tojson }}
+                        {%- endif %}
+                        {{- '}
+</tool_call>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '<|im_end|>
+' }}
+            {%- elif message.role == "tool" %}
+                {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+                    {{- '<|im_start|>user' }}
+                {%- endif %}
+                {{- '
+<tool_response>
+' }}
+                {{- content }}
+                {{- '
+</tool_response>' }}
+                {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+                    {{- '<|im_end|>
+' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endfor %}
+        {%- if add_generation_prompt %}
+            {{- '<|im_start|>assistant
+' }}
+        {%- endif %}

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 166100,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 166101,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10496,
+  "max_position_embeddings": 262144,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "group",
+          "symmetric": false,
+          "type": "int",
+          "zp_dtype": "torch.int8"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.13.1.a20260212"
+  },
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 70000000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 166144
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 166100,
+  "eos_token_id": 166101,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374aedadc1ea7ac4e42f9c147ca96d20c711e0e8b235c25863dc8e986e3ad713
+size 3303380160

recipe.yaml

@@ -0,0 +1,21 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      targets: [Linear]
+      ignore: [lm_head]
+      scheme: W4A16_ASYM
+      mappings:
+      - smooth_layer: re:.*input_layernorm$
+        balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*v_proj$
+        balance_layers: ['re:.*o_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*post_attention_layernorm$
+        balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*up_proj$
+        balance_layers: ['re:.*down_proj$']
+        activation_hook_target: null
+      duo_scaling: true
+      n_grid: 20

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19684f77ffbbe626fa5c77d4fac1d8069fe5770e1e6576d38f9e2813f2a43a7
+size 18451221

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb41d04798b714520a9b075727b0226538b7330254299062742c50ec8374bc36
+size 2782298

tokenizer_config.json

@@ -0,0 +1,102 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166100": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166101": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166102": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166103": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166104": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166105": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166106": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}